Mistral
mistraltextgen-2024
llm · Release Mar 10, 2024 · License n/a
A language model tailored for conversational agents, capable of engaging in multi-turn dialogues while maintaining context.
Modalities
What goes in and what comes out.
Inputs
text
Outputs
text
Capabilities
multi-turn dialogue, context retention, natural language understanding, sentiment analysis
Benchmarks snapshot
Structured JSON for reproducible comparisons.
{}Related on GenAIWiki
Same provider, tooling that cites the model, or prompts tuned for it.
Mistral
Mistral Large
Mistral Large supports up to 16k tokens with a response latency of 150ms, targeting enterprise-level applications and complex document understanding.
Mistral
Mixtral
Mixtral integrates large language processing with generative capabilities, managing up to 16,384 tokens while delivering high-quality content creation and response generation.